Automate ML research loops with ARIS skills
Use ARIS to run Markdown-based agent skills for literature review, idea discovery, cross-model critique, experiment planning, and paper-writing support.
npx skills add agentskillexchange/skills --skill automate-ml-research-loops-with-aris-skills
Use ARIS when an agent/operator needs a repeatable research loop for machine-learning work. The workflow is to install the ARIS skills or standalone CLI, run the structured research helpers, collect paper evidence, ask multiple reviewers to critique ideas or drafts, and keep experiment planning auditable.
What this skill actually does
Invoke this instead of a normal chat session when research work needs reusable prompts, helper scripts, cross-model review, and saved traces rather than a one-off answer. The boundary is autonomous ML research workflow support through skills and CLI helpers, not a general LLM framework or paper-writing product.
Inputs and prerequisites: ARIS skills or ARIS-Code CLI, Claude Code/Codex/OpenClaw-compatible agent, configured model providers.
Setup notes: Install the ARIS skill pack or download the latest ARIS-Code release, configure model providers, then invoke the relevant research skill from the supported agent runtime or CLI.
Source and verification boundary: use https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.